Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    select, chosen, selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मार्केट
    0.44
    商家
    0.41
    ContentAlignment
    0.40
     उत्
    0.40
    公益
    0.39
     маркетин
    0.39
     приез
    0.39
     क्रांतिक
    0.39
    iyeti
    0.39
     মার্চ
    0.38
    POSITIVE LOGITS
    select
    0.46
    short
    0.44
    selected
    0.43
    scalar
    0.41
    chosen
    0.39
    choose
    0.39
    =[]
    0.38
    niejsze
    0.38
     ਅਤੇ
    0.38
     laga
    0.38
    Act Density 0.003%

    No Known Activations